Spaces:
Paused
Paused
File size: 4,300 Bytes
0e759d2 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 |
import { Response } from "express";
import { v4 as uuidv4 } from "uuid";
import {
BatchScrapeRequest,
batchScrapeRequestSchema,
batchScrapeRequestSchemaNoURLValidation,
url as urlSchema,
RequestWithAuth,
ScrapeOptions,
BatchScrapeResponse,
} from "./types";
import {
addCrawlJobs,
finishCrawlKickoff,
getCrawl,
lockURLs,
saveCrawl,
StoredCrawl,
} from "../../lib/crawl-redis";
import { logCrawl } from "../../services/logging/crawl_log";
import { getJobPriority } from "../../lib/job-priority";
import { addScrapeJobs } from "../../services/queue-jobs";
import { callWebhook } from "../../services/webhook";
import { logger as _logger } from "../../lib/logger";
export async function batchScrapeController(
req: RequestWithAuth<{}, BatchScrapeResponse, BatchScrapeRequest>,
res: Response<BatchScrapeResponse>,
) {
if (req.body?.ignoreInvalidURLs === true) {
req.body = batchScrapeRequestSchemaNoURLValidation.parse(req.body);
} else {
req.body = batchScrapeRequestSchema.parse(req.body);
}
const id = req.body.appendToId ?? uuidv4();
const logger = _logger.child({
crawlId: id,
batchScrapeId: id,
module: "api/v1",
method: "batchScrapeController",
teamId: req.auth.team_id,
});
let urls = req.body.urls;
let invalidURLs: string[] | undefined = undefined;
if (req.body.ignoreInvalidURLs) {
invalidURLs = [];
let pendingURLs = urls;
urls = [];
for (const u of pendingURLs) {
try {
const nu = urlSchema.parse(u);
urls.push(nu);
} catch (_) {
invalidURLs.push(u);
}
}
}
logger.debug("Batch scrape " + id + " starting", {
urlsLength: urls.length,
appendToId: req.body.appendToId,
account: req.account,
});
if (!req.body.appendToId) {
await logCrawl(id, req.auth.team_id);
}
let { remainingCredits } = req.account!;
const useDbAuthentication = process.env.USE_DB_AUTHENTICATION === "true";
if (!useDbAuthentication) {
remainingCredits = Infinity;
}
const sc: StoredCrawl = req.body.appendToId
? ((await getCrawl(req.body.appendToId)) as StoredCrawl)
: {
crawlerOptions: null,
scrapeOptions: req.body,
internalOptions: { disableSmartWaitCache: true, teamId: req.auth.team_id }, // NOTE: smart wait disabled for batch scrapes to ensure contentful scrape, speed does not matter
team_id: req.auth.team_id,
createdAt: Date.now(),
};
if (!req.body.appendToId) {
await saveCrawl(id, sc);
}
let jobPriority = 20;
// If it is over 1000, we need to get the job priority,
// otherwise we can use the default priority of 20
if (urls.length > 1000) {
// set base to 21
jobPriority = await getJobPriority({
team_id: req.auth.team_id,
basePriority: 21,
});
}
logger.debug("Using job priority " + jobPriority, { jobPriority });
const scrapeOptions: ScrapeOptions = { ...req.body };
delete (scrapeOptions as any).urls;
delete (scrapeOptions as any).appendToId;
const jobs = urls.map((x) => {
return {
data: {
url: x,
mode: "single_urls" as const,
team_id: req.auth.team_id,
crawlerOptions: null,
scrapeOptions,
origin: "api",
crawl_id: id,
sitemapped: true,
v1: true,
webhook: req.body.webhook,
},
opts: {
jobId: uuidv4(),
priority: 20,
},
};
});
await finishCrawlKickoff(id);
logger.debug("Locking URLs...");
await lockURLs(
id,
sc,
jobs.map((x) => x.data.url),
);
logger.debug("Adding scrape jobs to Redis...");
await addCrawlJobs(
id,
jobs.map((x) => x.opts.jobId),
);
logger.debug("Adding scrape jobs to BullMQ...");
await addScrapeJobs(jobs);
if (req.body.webhook) {
logger.debug("Calling webhook with batch_scrape.started...", {
webhook: req.body.webhook,
});
await callWebhook(
req.auth.team_id,
id,
null,
req.body.webhook,
true,
"batch_scrape.started",
);
}
const protocol = process.env.ENV === "local" ? req.protocol : "https";
return res.status(200).json({
success: true,
id,
url: `${protocol}://${req.get("host")}/v1/batch/scrape/${id}`,
invalidURLs,
});
}
|